Sökning: id:"swepub:oai:DiVA.org:hh-20820" >
Terrain Classification and Classifier Fusion for Planetary Exploration Rovers
-
- Halatci, Ibrahim (författare)
- Massachusetts Institute of Technology, Department of Mechanical Engineering, 77 Massachusetts Avenue, Cambridge, MA 02139, United States
-
- Brooks, Christopher A. (författare)
- Massachusetts Institute of Technology, Department of Mechanical Engineering, 77 Massachusetts Avenue, Cambridge, MA 02139, United States
-
- Iagnemma, Karl (författare)
- Massachusetts Institute of Technology, Department of Mechanical Engineering, 77 Massachusetts Avenue, Cambridge, MA 02139, United States
-
(creator_code:org_t)
- Piscataway : IEEE Press, 2007
- Engelska.
-
Ingår i: Aerospace Conference, 2007 IEEE. - Piscataway : IEEE Press. - 1424405254 - 9781424405244 ; , s. 1-11
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Knowledge of the physical properties of terrain surrounding a planetary exploration rover can be used to allow a rover system to fully exploit its mobility capabilities. Here a study of multi-sensor terrain classification for planetary rovers in Mars and Mars-like environments is presented. Two classification algorithms for color, texture, and range features are presented based on maximum likelihood estimation and support vector machines. In addition, a classification method based on vibration features derived from rover wheel-terrain interaction is briefly described. Two techniques for merging the results of these "low-level" classifiers are presented that rely on Bayesian fusion and meta-classifier fusion. The performance of these algorithms is studied using images from NASA's Mars Exploration Rover mission and through experiments on a four-wheeled test-bed rover operating in Mars-analog terrain. It is shown that accurate terrain classification can be achieved via classifier fusion from visual and tactile features.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
Nyckelord
- Bayesian methods
- Classification algorithms
- Layout
- Mars
- Maximum likelihood estimation
- Merging
- Support vector machine classification
- Support vector machines
- Testing
- Wheels
- Bayes methods
- Image classification
- Image colour analysis
- Image texture
- Maximum likelihood estimation
- Planetary rovers
- Sensor fusion
- Support vector machines
- Bayesian fusion
- Mars
- NASA Mars Exploration Rover mission
- Classifier fusion
- Four-wheeled test-bed rover
- Maximum likelihood estimation
- Meta-classifier fusion
- Multi-sensor terrain classification
- Planetary exploration rovers
- Rover wheel-terrain interaction
- Support vector machines
- Vibration features
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)